© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110617
    Prev
    Next
    INDEX
    Explanations

    python unit tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atorship
    -0.84
     Moody
    -0.77
    Moody
    -0.75
    вец
    -0.73
    ണ
    -0.72
     buckling
    -0.71
     Executes
    -0.70
    getRuntime
    -0.70
     proverb
    -0.69
    ミス
    -0.68
    POSITIVE LOGITS
     unittest
    1.13
    unittest
    1.10
     test
    1.00
    TestCase
    0.96
     setUp
    0.95
     TestCase
    0.94
    assertRaises
    0.92
     descubre
    0.86
    tearDown
    0.82
     Test
    0.81
    Activations Density 0.012%

    No Known Activations